Semilattice

semilattice.link/4kZ13Tb

DM to talk about:
- a custom model of your audience
- a custom agent for your use case or client
- MCP and API for your agents

It uses the Semilattice API to predict specific audiences. Accuracy is benchmarked at >87% and results arrive in <20 seconds.

The agent can answer simple questions for day-to-day unknowns or construct multi-step explorations to get to the bottom of a problem.

Audience Chat lets you discover things about your audience in seconds. Whenever you’re thinking about user problems, market trends, or customer insights—just open a tab and ask.

Connect to Semilattice MCP - Semilattice Learn how to connect your AI assistant, IDE, or agentic tooling to Semilattice MCP

It’s powered by the Semilattice API, so audience models have known accuracy, predictions take ~15 seconds, and you can view everything in the dashboard.

Visit the docs to add the MCP to ChatGPT, Claude, and other AI clients: semilattice.link/2M9BQPW

You can say something like “use Semilattice to research how designers are using AI” and it'll select the right audience model, come up with research questions, run simulations, and summarise results. You can even ask for a PDF.

We’ve launched an MCP server for Semilattice—a tool for LLMs so they can do computational research for you.

It's only possible with simulated audiences. Otherwise you're stuck on question one for hours, days, weeks; or having to come up with all the questions in advance. Or just not bothering.

You need answers as quickly as possible to inform new questions, new branches. The tool keeps track of where you've been, letting you go back to explore different paths; letting you zoom out and take it all in.

This demo attempts to mirror how your brain thinks about research: rapid questions branching off in different directions on different topics—some followed, others not.

semilattice.link/5s0l24h

Data Journalists Global data journalists model based on 2023 State of Data Journalism survey

See it spin at a reasonable speed here: semilattice.ai/populations/...

We added this 3D visualisation to our models in the Semilattice dashboard. It shows model data in a 3D space so you can easily spot semantic similarities. BUT, the most important question is: How fast can we spin this thing? 🌀

The answer: over 8,333 orbits per second!

You could get a model of your customers, users of a specific feature, a new target segment—any audience you can describe.

And when you’ve got a model, you can use it to accurately predict new questions. E.g. to test copy, explore jobs to be done, prioritise features, understand personas, etc.

It’s easy to make new audience models with Semilattice, you just upload some survey data—but not everyone has data!

So we’re offering to build audience models for you. Just let us know the audience you want, and we’ll work out how to source the data and build it.

semilattice.link/x6dSjYO

Our latest demo takes a B2B website URL, uses Semilattice to run PMF-focused audience predictions, and then generates a PDF report with a big score /100.

Try it here: semilattice.link/TuQufH9

We’re building demos to show what’s possible. Our focus is the API, not the apps. DM to build something!

To celebrate the launch of Tron Ares, we made a video game. It's more like Family Feud though.

You play against the Semilattice API at predicting your audience 🕹️

Play here: semilattice.link/Ar7TmMe

The Semilattice API: user insights as infrastructure · Semilattice Predict user behaviour like you make database queries.

What happens when you can predict user behaviour like you make database queries?

When user behaviour data has the cost structure of a database query instead of a consulting engagement, it prompts a rethink. A big rethink.

Read the blog to learn more: semilattice.link/rXhKQkM